AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Incorporating Knowledge Graph Embeddings into Topic Modeling

Liang Yao, Yin Zhang, Baogang Wei, Zhe Jin, Rui Zhang, Yangyang Zhang, Qinfei Chen

AAAI 2017 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 60 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace words-only topics with TransE entity-embedding knowledge (KGE-LDA(a))LDA · 20NG, NIPS, OhsumedPMI topic coherenceImproved
add entity embeddings (KGE-LDA(a))LDA · 20NG document classification K=45accuracy: 0.693 -> 0.705Improved
add entity embeddings (KGE-LDA(a))LDA · Ohsumed document classification K=45accuracy: 0.476 -> 0.490Improved
add raw linked entities (CI-LDA, Corr-LDA) instead of embeddingsLDA · 20NG, NIPS, OhsumedPMI topic coherenceNo clear effect
add raw linked entities (Corr-LDA)LDA · 20NG classification K=45accuracy: 0.693 -> 0.684No clear effect
add WordNet must-links (GK-LDA)LDA · OhsumedPMI topic coherenceHurt
add WordNet must-links (GK-LDA)LDA · 20NG and NIPSPMI topic coherenceImproved
add Wikipedia word vectors (LF-LDA)LDA · 20NG vs NIPS and OhsumedPMI topic coherenceMixed
add concept-topic model knowledge (CTM)LDA · 20NG classification K=45accuracy: 0.693 -> 0.312Hurt
use KGE-LDA(a) instead of LDALDA · 20NG email topic K=30PMI topic coherence: 67.181 -> 89.216Improved
use KGE-LDA(a) instead of LDALDA · 20NG computer topic K=30PMI topic coherence: 58.594 -> 84.378Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy